Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond annotations: discloses credit spend, draft-study restriction, that answers become a labeled synthetic result set never counted as responses, the background/async nature, and the possible needs_confirmation envelope.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly five dense sentences, front-loaded with the core action, then cost, prerequisites, results, and follow-up. Every sentence earns its place with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a background, credit-spending run with no output schema, it covers the full lifecycle (estimate → run → get), the confirmation edge case, and the synthetic labeling. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds meaning for the 'kind' modes and the interview behavior, but with 70% schema coverage most parameters are already documented. It doesn't explain budgetUsd, approvalId, or workspace beyond what the schema provides, so it is above baseline but not complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Starts a background run: every person on the panel answers the study') and distinguishes the two modes (survey answers vs interview sits with the study's interviewer). Clearly distinct from siblings like prism_panel_runs_get and prism_panel_runs_estimate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says what to do before ('give the person the estimate from prism_panel_runs_estimate first') and after ('Follow with prism_panel_runs_get'), and notes the prerequisite that it works on draft studies. Names alternatives by their sibling names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.